Related papers: Domain Invariant Representation Learning and Sleep…

Model-Based Reinforcement Learning distinguishes between physical dynamics models operating on proprioceptive inputs and latent dynamics models operating on high-dimensional image observations. A prominent latent approach is the Recurrent…

Neural models are increasingly used in Web-scale Information Retrieval (IR). However, relying on these models introduces substantial computational and energy requirements, leading to increasing attention toward their environmental cost and…

Humans have been aware for thousands of years that sleep comes in many forms, accompanied by different kinds of mental content. We review the first-person report literature on the frequency and type of content experienced in various stages…

Sleep is essential for learning and cognition, but the mechanisms by which it stabilizes learning, supports creativity, and manages the energy consumption of networks engaged in post-sleep task have not been yet modelled. During sleep, the…

Learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning and control. The problem has recently been studied from a generative perspective…

Studies show that the representations learned by deep neural networks can be transferred to similar prediction tasks in other domains for which we do not have enough labeled data. However, as we transition to higher layers in the model, the…

Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious,…

Sleep studies are important for diagnosing sleep disorders such as insomnia, narcolepsy or sleep apnea. They rely on manual scoring of sleep stages from raw polisomnography signals, which is a tedious visual task requiring the workload of…

Sleep disorders, such as sleep apnea, parasomnias, and hypersomnia, affect 50-70 million adults in the United States (Hillman et al., 2006). Overnight polysomnography (PSG), including brain monitoring using electroencephalography (EEG), is…

We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in…

Automated sleep stage classification typically employs a single population-agnostic model, disregarding established demographic variations in sleep architecture. Sleep patterns, however, differ substantially across gender, age, and…

Image alignment across domains has recently become one of the realistic and popular topics in the research community. In this problem, a deep learning-based image alignment method is usually trained on an available largescale database.…

Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian…

Self-supervised learning of speech representations has been a very active research area but most work is focused on a single domain such as read audio books for which there exist large quantities of labeled and unlabeled data. In this…

Despite the impressive advances achieved using deep learning for functional brain activity analysis, the heterogeneity of functional patterns and the scarcity of imaging data still pose challenges in tasks such as identifying neurological…

Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions. However, these simulations are non-differentiable, forcing…

We introduce the Dreaming $L$-directional Associative Memory (DLAM), a multi-layer Hebbian architecture in which off-line dreaming and supervised heteroassociative coupling coexist within a single energy function, placing our approach…

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an…

The process of digitising histology slides involves multiple factors that can affect a whole slide image's (WSI) final appearance, including the staining protocol, scanner, and tissue type. This variability constitutes a domain shift and…

It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features. In this work, we propose "Amending Inherent Interpretability via Self-Supervised Masking" (AIM), a simple yet interestingly effective…